GPT-5 Mini
GPT-5 MiniAlternatives?
CheaperGPT-6 Lunahigh×7.4-46%$0.029Function calling only with none · Chat Completions+3
OpenDeepSeek V4.1 Flash 1017max×10.3+390%$0.26Pass back reasoning_content · Chat Completions+4CheaperGPT-5.6 Lunahigh×5.5-18%$0.044
CheaperClaude Haiku 5.5medium×4.4-12%$0.047Remove sampling parameters+5ICheaperK2 Horizon 7BthinkingOpen×3.2-24%$0.30 / $1.20No image inputGPT-6 Lunahigh×7.4-46%$0.029Function calling only with none · Chat Completions+3GPT-5.6 Lunahigh×5.5-18%$0.044Claude Haiku 5.5medium×4.4-12%$0.047Remove sampling parameters+5IK2 Horizon 7BthinkingOpen×3.2-24%$0.30 / $1.20No image input
MiMo v2.5thinkingOpen×2.8-64%$0.019GPT-6 Lunalow+86%-92%$0.005Function calling only with none · Chat Completions+3GPT-5.6 Lunalow+80%-82%$0.01MiMo v2.5thinkingOpen×2.8-64%$0.019Claude Haiku 5.5low×3.5-54%$0.024Remove sampling parameters+5MiMo v2.5 ProthinkingOpen×2.1same$0.054No image inputDeepSeek V4.1 Flash 1017maxOpen×10.3+390%$0.26Pass back reasoning_content · Chat Completions+4MiMo v2.6 FlashthinkingOpen×9.9+17%$0.062Pass back reasoning_content+3
GLM 5.3maxOpen×9.6+3,649%$2.01No image input+4
Ling 3.1 FlashOpen×9.5+1,769%$1.00No image inputGLM 5.3 FlashmaxOpen×9.3+430%$0.28Defaults to max · Self-hosted+4GPT-6 Astrahigh×10.3+3,125%$1.73Monitoring can return HTTP 403+2GPT-6.1 Solhigh×9.9+497%$0.32Remove unsupported parameters+5GPT-6 Solhigh×9.3+597%$0.37GPT-5.6 Solhigh×8.5+1,410%$0.81GPT-6 Lunahigh×7.4-46%$0.029Function calling only with none · Chat Completions+3GPT-5.5high×6.8+2,781%$1.54Prompts with >272K input tokensGPT-5.6 Terrahigh×6.5+532%$0.34Prompts with >272K input tokensGPT-5.5 Instant (June 2026)×5.6+1,193%$0.69All OpenAI models →History
7 versionsBenchmarks
in Agents & Tool UseFAQ
How much does GPT-5 Mini cost?›
$0.25 per 1M input tokens and $2 per 1M output tokens; cached input $0.025 per 1M. A typical benchmark task costs about $0.053 at high effort.
Is GPT-5 Mini free to use?›
There is no free API; the cheapest paid price is $0.25 per 1M input tokens.
How good is GPT-5 Mini, and what is it best at?›
#118 of 334 in Chat & Knowledge, #75 of 132 in Coding, #79 of 133 in Agents & Tool Use, #116 of 195 in Writing & Language, #68 of 124 in Vision & Documents. Strongest at: Instructions.
Is GPT-5 Mini better than Gemini 3.1 Flash Lite?›
On AutomationBench-AA, GPT-5 Mini scores 6.5 vs 6.8 — about the same. It is 11% cheaper per task.
How can I use GPT-5 Mini?›
Through the API of Azure, OpenAI.
What is the context window of GPT-5 Mini?›
400K tokens, with up to 128K output tokens.
When was GPT-5 Mini released? Is there a newer version?›
Released 2025-08-07. It has been superseded by GPT-5.4 Mini.
Is GPT-5 Mini open source?›
No, GPT-5 Mini is a closed model available through an API. The closest open-weights option here is DeepSeek V4.1 Flash 1017.
Can GPT-5 Mini read images?›
It accepts text and images, PDF files as input.
What is GPT-5 Mini?›
GPT-5 Mini is a closed language model from OpenAI, released Aug 2025, the successor to GPT-4.1 Mini.
What are the best alternatives to GPT-5 Mini?›
GPT-6 Luna (cheaper), DeepSeek V4.1 Flash 1017 (open weights).